Bimodal automated carotid ultrasound segmentation using geometrically constrained deep neural networks

Azzopardi, Carl, Camilleri, Kenneth and Hicks, Yulia Alexandrovna ORCID: https://orcid.org/0000-0002-7179-4587 2020. Bimodal automated carotid ultrasound segmentation using geometrically constrained deep neural networks. IEEE Journal of Biomedical and Health Informatics 24 (4) , pp. 1004-1015. 10.1109/JBHI.2020.2965088

Preview

PDF - Accepted Post-Print Version Download (2MB) | Preview

Abstract

For asymptomatic patients suffering from carotid stenosis, the assessment of plaque morphology is an important clinical task which allows monitoring of the risk of plaque rupture and future incidents of stroke. Ultrasound Imaging provides a safe and non-invasive modality for this, and the segmentation of media-adventitia boundaries and lumen-intima boundaries of the Carotid artery form an essential part in this monitoring process. In this paper, we propose a novel Deep Neural Network as a fully automated segmentation tool, and its application in delineating both the media-adventitia boundary and the lumen-intima boundary. We develop a new geometrically constrained objective function as part of the Network's Stochastic Gradient Descent optimisation, thus tuning it to the problem at hand. Furthermore, we also apply a bimodal fusion of amplitude and phase congruency data proposed by us in previous work, as an input to the network, as the latter provides an intensity-invariant data source to the network. We finally report the segmentation performance of the network on transverse sections of the carotid. Tests are carried out on an augmented dataset of 81,000 images, and the results are compared to other studies by reporting the DICE coefficient of similarity, modified Hausdorff Distance, sensitivity and specificity. Our proposed modification is shown to yield improved results on the standard network over this larger dataset, with the advantage of it being fully automated. We conclude that Deep Neural Networks provide a reliable trained manner in which carotid ultrasound images may be automatically segmented, using amplitude data and intensity invariant phase congruency maps as a data source.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
ISSN:	2168-2194
Date of First Compliant Deposit:	30 January 2020
Date of Acceptance:	7 November 2019
Last Modified:	07 Nov 2023 13:40
URI:	https://orca.cardiff.ac.uk/id/eprint/129192

Citation Data

Cited 10 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item